Functions for descriptive statistics

You can make tables summarizing descriptive statistics easily with webr package.

Installation of packages

You have to install the latest versions of “webr” and “moonBook” packages from github.

if(!require(devtools)) install.packages("devtools")
devtools::install_github("cardiomoon/webr")
devtools::install_github("cardiomoon/moonBook")   # For examples
devtools::install_github("cardiomoon/rrtable")    # For reproducible research

Load packages

require(webr)
require(moonBook) # For data acs

Summarizing Frequencies

You can summmarize the frequencies easily with freqSummary() function. Also you can make a table summarizng frequencies with freqTable() function.

freqSummary(acs$Dx)

                Count Percent Valid Percent Cum Percent
NSTEMI          "153" "17.9"  "17.9"        "17.9"     
STEMI           "304" "35.5"  "35.5"        "53.3"     
Unstable Angina "400" "46.7"  "46.7"        "100.0"    
Sum             "857" "100.0" "100.0"       ""

freqTable(acs$Dx)

rowname	Count	Percent	Valid Percent	Cum Percent
NSTEMI	153	17.9	17.9	17.9
STEMI	304	35.5	35.5	53.3
Unstable Angina	400	46.7	46.7	100.0
Sum	857	100.0	100.0

Ready for reproducible research

The freqTable() function returns an object of class “flextable”. With this object, you can make html, pdf, docx, pptx file easily.

result=freqTable(acs$Dx)
class(result)

[1] "flextable"

Frequency table for a continuous variable

You can make the frequency table for a continuous variable. In this time, you can get a long table.

freqTable(mtcars$mpg)

rowname	Count	Percent	Valid Percent	Cum Percent
10.4	2	6.2	6.2	6.2
13.3	1	3.1	3.1	9.4
14.3	1	3.1	3.1	12.5
14.7	1	3.1	3.1	15.6
15	1	3.1	3.1	18.8
15.2	2	6.2	6.2	25.0
15.5	1	3.1	3.1	28.1
15.8	1	3.1	3.1	31.2
16.4	1	3.1	3.1	34.4
17.3	1	3.1	3.1	37.5
17.8	1	3.1	3.1	40.6
18.1	1	3.1	3.1	43.8
18.7	1	3.1	3.1	46.9
19.2	2	6.2	6.2	53.1
19.7	1	3.1	3.1	56.2
21	2	6.2	6.2	62.5
21.4	2	6.2	6.2	68.8
21.5	1	3.1	3.1	71.9
22.8	2	6.2	6.2	78.1
24.4	1	3.1	3.1	81.2
26	1	3.1	3.1	84.4
27.3	1	3.1	3.1	87.5
30.4	2	6.2	6.2	93.8
32.4	1	3.1	3.1	96.9
33.9	1	3.1	3.1	100.0
Sum	32	100.0	100.0

Frequency table for two categorical variables

You can make a table summarizing the independency of two categorical variables.

x2Table(acs,Dx,sex)

rowname	Female	Male	Total
NSTEMI	50 (32.7%)	103 (67.3%)	153 (100 %)
STEMI	84 (27.6%)	220 (72.4%)	304 (100 %)
Unstable Angina	153 (38.2%)	247 (61.8%)	400 (100 %)
Total	287 (33.5%)	570 (66.5%)	857 (100 %)
Chi-squared=8.798, df=2, Cramer's V=0.101, Chi-squared p=0.0123

You can make a table with columnwise percentages.

x2Table(acs,Dx,sex,margin=2)

rowname	Female	Male	Total
NSTEMI	50 (17.4%)	103 (18.1%)	153 (17.9%)
STEMI	84 (29.3%)	220 (38.6%)	304 (35.5%)
Unstable Angina	153 (53.3%)	247 (43.3%)	400 (46.7%)
Total	287 (100 %)	570 (100 %)	857 (100 %)
Chi-squared=8.798, df=2, Cramer's V=0.101, Chi-squared p=0.0123

You can hide pecentages.

x2Table(acs,Dx,sex,show.percent=FALSE)

rowname	Female	Male	Total
NSTEMI	50	103	153
STEMI	84	220	304
Unstable Angina	153	247	400
Total	287	570	857
Chi-squared=8.798, df=2, Cramer's V=0.101, Chi-squared p=0.0123

Numerical summary

Numerical summary of a vector

You can make a numerical summary table with numSummary() function. If you use the numSummary() function to a continuous vector, you can get the following summary. This function uses psych::describe function

require(dplyr)
numSummary(acs$age)

# A tibble: 1 × 12
      n  mean    sd median trimmed   mad   min   max range   skew kurtosis    se
  <dbl> <dbl> <dbl>  <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>    <dbl> <dbl>
1   857  63.3  11.7     64    63.6  13.3    28    91    63 -0.175   -0.566 0.400

numSummaryTable(acs$age)

n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
857.00	63.31	11.70	64.00	63.56	13.34	28.00	91.00	63.00	-0.18	-0.57	0.40

Numerical summary of a data.frame or a tibble

You can make a numerical summary of a data.frame. The numSummary function uses is.numeric function to select numeric columns and make a numeric summary.

numSummary(acs)

# A tibble: 9 × 13
  vars      n  mean    sd median trimmed   mad   min   max range   skew kurtosis
  <chr> <dbl> <dbl> <dbl>  <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>    <dbl>
1 age     857  63.3 11.7    64      63.6 13.3   28    91    63   -0.175  -0.566 
2 EF      723  55.8  9.62   58.1    56.8  7.86  18    79    61   -0.978   1.11  
3 heig…   764 163.   9.08  165     164.   7.41 130   185    55   -0.440  -0.0145
4 weig…   766  64.8 11.4    65      64.5 10.4   30   112    82    0.336   0.444 
5 BMI     764  24.3  3.35   24.2    24.2  3.01  15.6  41.4  25.8  0.668   2.12  
6 TC      834 185.  47.8   183     184.  43.0   25   493   468    0.737   3.77  
7 LDLC    833 117.  41.1   114     115.  40.0   15   366   351    0.787   2.33  
8 HDLC    834  38.2 11.1    38      38.0 10.4    4    89    85    0.366   1.46  
9 TG      842 125.  90.9   106.    111.  60.0   11   877   866    3.02   14.9   
# ℹ 1 more variable: se <dbl>

numSummaryTable(acs)

rowname	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
1	age	857.00	63.31	11.70	64.00	63.56	13.34	28.00	91.00	63.00	-0.18	-0.57	0.40
2	EF	723.00	55.83	9.62	58.10	56.77	7.86	18.00	79.00	61.00	-0.98	1.11	0.36
3	height	764.00	163.18	9.08	165.00	163.52	7.41	130.00	185.00	55.00	-0.44	-0.01	0.33
4	weight	766.00	64.84	11.36	65.00	64.55	10.38	30.00	112.00	82.00	0.34	0.44	0.41
5	BMI	764.00	24.28	3.35	24.16	24.16	3.01	15.62	41.42	25.80	0.67	2.12	0.12
6	TC	834.00	185.20	47.77	183.00	183.76	43.00	25.00	493.00	468.00	0.74	3.77	1.65
7	LDLC	833.00	116.58	41.09	114.00	114.62	40.03	15.00	366.00	351.00	0.79	2.33	1.42
8	HDLC	834.00	38.24	11.09	38.00	37.95	10.38	4.00	89.00	85.00	0.37	1.46	0.38
9	TG	842.00	125.24	90.85	105.50	111.29	60.05	11.00	877.00	866.00	3.02	14.91	3.13

Use of dplyr::group_by() and dplyr::select() function to summarize

You can use dplyr::select() function to select variables to summarize.

acs %>% select(age,EF) %>% numSummary

# A tibble: 2 × 13
  vars      n  mean    sd median trimmed   mad   min   max range   skew kurtosis
  <chr> <dbl> <dbl> <dbl>  <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>    <dbl>
1 age     857  63.3 11.7    64      63.6 13.3     28    91    63 -0.175   -0.566
2 EF      723  55.8  9.62   58.1    56.8  7.86    18    79    61 -0.978    1.11 
# ℹ 1 more variable: se <dbl>

acs %>% select(age,EF) %>% numSummaryTable

rowname	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
1	age	857.00	63.31	11.70	64.00	63.56	13.34	28.00	91.00	63.00	-0.18	-0.57	0.40
2	EF	723.00	55.83	9.62	58.10	56.77	7.86	18.00	79.00	61.00	-0.98	1.11	0.36

You can use dplyr::group_by() and dplyr::select() function to select variables to summarize by group.

acs %>% group_by(sex) %>% select(age,EF) %>% numSummary

# A tibble: 4 × 14
  sex    vars      n  mean    sd median trimmed   mad   min   max range    skew
  <chr>  <chr> <dbl> <dbl> <dbl>  <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>   <dbl>
1 Male   age     570  60.6 11.2    61      60.6 11.9   28      91  63   -0.0148
2 Male   EF      483  55.6  9.40   57.3    56.4  8.01  18      79  61   -0.789 
3 Female age     287  68.7 10.7    70      69.4 10.4   39      90  51   -0.593 
4 Female EF      240  56.3 10.1    59.2    57.6  7.19  18.4    75  56.6 -1.30  
# ℹ 2 more variables: kurtosis <dbl>, se <dbl>

acs %>% group_by(sex) %>% select(age,EF) %>% numSummaryTable

sex	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
Male	age	570.00	60.61	11.23	61.00	60.65	11.86	28.00	91.00	63.00	-0.01	-0.36	0.47
Male	EF	483.00	55.62	9.40	57.30	56.38	8.01	18.00	79.00	61.00	-0.79	0.76	0.43
Female	age	287.00	68.68	10.73	70.00	69.43	10.38	39.00	90.00	51.00	-0.59	-0.26	0.63
Female	EF	240.00	56.27	10.06	59.25	57.57	7.19	18.40	75.00	56.60	-1.30	1.70	0.65

You can summarize by multiple groups.

acs %>% group_by(sex,Dx) %>% select(age,EF) %>% numSummary

# A tibble: 12 × 15
   sex    Dx      vars      n  mean    sd median trimmed   mad   min   max range
   <chr>  <chr>   <chr> <dbl> <dbl> <dbl>  <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>
 1 Male   STEMI   age     220  59.4 11.7    59.5    59.4 11.1   30    86    56  
 2 Male   STEMI   EF      195  52.4  8.90   54      52.9  8.45  18    73.6  55.6
 3 Female STEMI   age      84  69.1 10.4    70      70.0 10.4   42    89    47  
 4 Female STEMI   EF       77  52.3 10.9    55.7    53.7  9.04  18.4  67.1  48.7
 5 Male   NSTEMI  age     103  61.1 11.6    59      61.3 13.3   28    85    57  
 6 Male   NSTEMI  EF       94  55.1  9.42   58      55.9  7.12  21.8  74    52.2
 7 Female Unstab… age     153  67.7 10.7    70      68.3  8.90  39    90    51  
 8 Female Unstab… EF      118  59.4  8.76   61.1    60.8  5.49  22    71.9  49.9
 9 Male   Unstab… age     247  61.4 10.6    61      61.4 10.4   35    91    56  
10 Male   Unstab… EF      194  59.1  8.67   60      60.2  5.93  24.7  79    54.3
11 Female NSTEMI  age      50  70.9 11.4    74.5    71.9  8.90  42    88    46  
12 Female NSTEMI  EF       45  54.8  9.10   57      55.3  9.79  36.8  75    38.2
# ℹ 3 more variables: skew <dbl>, kurtosis <dbl>, se <dbl>

acs %>% group_by(sex,Dx) %>% select(age,EF) %>% numSummaryTable

sex	Dx	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
Male	STEMI	age	220.00	59.43	11.72	59.50	59.43	11.12	30.00	86.00	56.00	0.00	-0.55	0.79
Male	STEMI	EF	195.00	52.37	8.90	54.00	52.88	8.45	18.00	73.60	55.60	-0.62	0.53	0.64
Female	STEMI	age	84.00	69.11	10.36	70.00	70.04	10.38	42.00	89.00	47.00	-0.65	-0.09	1.13
Female	STEMI	EF	77.00	52.32	10.94	55.70	53.72	9.04	18.40	67.10	48.70	-1.17	1.01	1.25
Male	NSTEMI	age	103.00	61.15	11.57	59.00	61.28	13.34	28.00	85.00	57.00	-0.11	-0.53	1.14
Male	NSTEMI	EF	94.00	55.08	9.42	58.00	55.86	7.12	21.80	74.00	52.20	-0.83	0.57	0.97
Female	Unstable Angina	age	153.00	67.72	10.67	70.00	68.33	8.90	39.00	90.00	51.00	-0.54	-0.34	0.86
Female	Unstable Angina	EF	118.00	59.40	8.76	61.10	60.79	5.49	22.00	71.90	49.90	-1.86	4.06	0.81
Male	Unstable Angina	age	247.00	61.44	10.57	61.00	61.41	10.38	35.00	91.00	56.00	0.07	-0.15	0.67
Male	Unstable Angina	EF	194.00	59.14	8.67	60.00	60.15	5.93	24.70	79.00	54.30	-1.25	2.54	0.62
Female	NSTEMI	age	50.00	70.88	11.35	74.50	71.88	8.90	42.00	88.00	46.00	-0.72	-0.34	1.61
Female	NSTEMI	EF	45.00	54.85	9.10	57.00	55.26	9.79	36.80	75.00	38.20	-0.32	-0.83	1.36

For reproducible research

You can use package rrtable for reproducible research.

require(rrtable)
type=c("table","table")
title=c("Frequency Table","Numerical Summary")
code=c("freqTable(acs$Dx)","acs %>% group_by(sex) %>% select(EF,age) %>% numSummaryTable")
data=data.frame(type,title,code,stringsAsFactors = FALSE)
data2pptx(data)

Making File: 123

[1] "/tmp/RtmpFqbmKo/Rbuild1d6345cd72a5/webr/vignettes/./Report.pptx"

data2docx(data)

Making File: 123

[1] "/tmp/RtmpFqbmKo/Rbuild1d6345cd72a5/webr/vignettes/./Report.docx"